===================================================================
@@ -4248,7 +4248,8 @@ rs6000_option_override (void)
static tree
rs6000_builtin_mask_for_load (void)
{
- if (TARGET_ALTIVEC || TARGET_VSX)
+ /* Don't use lvsl/vperm for P8. */
+ if ((TARGET_ALTIVEC || TARGET_VSX) && rs6000_cpu != PROCESSOR_POWER8)
return altivec_builtin_mask_for_load;
else
return 0;
@@ -4327,6 +4328,10 @@ rs6000_builtin_support_vector_misalignment (machin
{
if (TARGET_VSX)
{
+ /* P8 supports all misalignments. */
+ if (rs6000_cpu == PROCESSOR_POWER8)
+ return true;
+
/* Return if movmisalign pattern is not supported for this mode. */
if (optab_handler (movmisalign_optab, mode) == CODE_FOR_nothing)
return false;
@@ -4390,6 +4395,9 @@ rs6000_builtin_vectorization_cost (enum vect_cost_
return 3;
case unaligned_load:
+ if (TARGET_VSX && rs6000_cpu == PROCESSOR_POWER8)
+ return 1;
+
if (TARGET_VSX && TARGET_ALLOW_MOVMISALIGN)
{
elements = TYPE_VECTOR_SUBPARTS (vectype);
@@ -4425,6 +4433,9 @@ rs6000_builtin_vectorization_cost (enum vect_cost_
return 2;
case unaligned_store:
+ if (TARGET_VSX && rs6000_cpu == PROCESSOR_POWER8)
+ return 1;
+
if (TARGET_VSX && TARGET_ALLOW_MOVMISALIGN)
{
elements = TYPE_VECTOR_SUBPARTS (vectype);
===================================================================
@@ -910,7 +910,8 @@
(define_expand "movmisalign<mode>"
[(set (match_operand:VEC_N 0 "nonimmediate_operand" "")
(match_operand:VEC_N 1 "any_operand" ""))]
- "VECTOR_MEM_VSX_P (<MODE>mode) && TARGET_ALLOW_MOVMISALIGN"
+ "VECTOR_MEM_VSX_P (<MODE>mode) &&
+ (TARGET_ALLOW_MOVMISALIGN || rs6000_cpu == PROCESSOR_POWER8)"
"")
;; Vector shift right in bits. Currently supported ony for shift
===================================================================
@@ -54,7 +54,9 @@ int main (void)
return 0;
}
-/* { dg-final { scan-tree-dump-times "basic block vectorized" 1 "slp1" { target vect_element_align } } } */
+/* Exclude POWER8 (only POWER cpu for which vect_element_align is true)
+ because loops have vectorized before SLP gets a shot. */
+/* { dg-final { scan-tree-dump-times "basic block vectorized" 1 "slp1" { target { vect_element_align && { ! powerpc*-*-* } } } } } */
/* { dg-final { cleanup-tree-dump "slp1" } } */
/* { dg-final { cleanup-tree-dump "slp2" } } */
===================================================================
@@ -54,7 +54,9 @@ int main (void)
return 0;
}
-/* { dg-final { scan-tree-dump-times "basic block vectorized" 1 "slp1" { target vect_element_align } } } */
+/* Exclude POWER8 (only POWER cpu for which vect_element_align is true)
+ because loops have vectorized before SLP gets a shot. */
+/* { dg-final { scan-tree-dump-times "basic block vectorized" 1 "slp1" { target { vect_element_align && { ! powerpc*-*-* } } } } } */
/* { dg-final { cleanup-tree-dump "slp1" } } */
/* { dg-final { cleanup-tree-dump "slp2" } } */
===================================================================
@@ -54,7 +54,9 @@ int main (void)
return 0;
}
-/* { dg-final { scan-tree-dump-times "basic block vectorized" 1 "slp1" { target { vect_int_mult && vect_element_align } } } } */
+/* Exclude POWER8 (only POWER cpu for which vect_element_align is true)
+ because loops have vectorized before SLP gets a shot. */
+/* { dg-final { scan-tree-dump-times "basic block vectorized" 1 "slp1" { target { { vect_int_mult && vect_element_align } && { ! powerpc*-*-* } } } } } */
/* { dg-final { cleanup-tree-dump "slp1" } } */
/* { dg-final { cleanup-tree-dump "slp2" } } */
===================================================================
@@ -19,5 +19,5 @@ int foo (int *p)
return tem0 + tem1 + tem2 + tem3;
}
-/* { dg-final { scan-tree-dump "vectorization is not profitable" "slp2" { xfail vect_no_align } } } */
+/* { dg-final { scan-tree-dump "vectorization is not profitable" "slp2" { xfail { vect_no_align && { ! vect_hw_misalign } } } } } */
/* { dg-final { cleanup-tree-dump "slp2" } } */
===================================================================
@@ -46,6 +46,6 @@ int main (void)
return 0;
}
-/* { dg-final { scan-tree-dump-times "basic block vectorized" 1 "slp2" { xfail vect_no_align } } } */
+/* { dg-final { scan-tree-dump-times "basic block vectorized" 1 "slp2" { xfail { vect_no_align && { ! vect_hw_misalign } } } } } */
/* { dg-final { cleanup-tree-dump "slp2" } } */
===================================================================
@@ -40,5 +40,5 @@ int main (void)
return main1 ();
}
-/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 0 "vect" } } */
+/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 0 "vect" { target { ! vect_hw_misalign } } } } */
/* { dg-final { cleanup-tree-dump "vect" } } */
===================================================================
@@ -47,5 +47,5 @@ int main (void)
}
/* { dg-final { scan-tree-dump-times "vectorization not profitable" 1 "vect" } } */
-/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 0 "vect" } } */
+/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 0 "vect" { target { ! vect_hw_misalign } } } } */
/* { dg-final { cleanup-tree-dump "vect" } } */
===================================================================
@@ -43,8 +43,8 @@ int main (void)
}
/* Peeling to align the store is used. Overhead of peeling is too high. */
-/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 0 "vect" { target vector_alignment_reachable } } } */
-/* { dg-final { scan-tree-dump-times "vectorization not profitable" 1 "vect" { target { vector_alignment_reachable && {! vect_no_align} } } } } */
+/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 0 "vect" { target { vector_alignment_reachable && {! vect_no_align} } } } } */
+/* { dg-final { scan-tree-dump-times "vectorization not profitable" 1 "vect" { target { vector_alignment_reachable && {! vect_hw_misalign} } } } } */
/* Versioning to align the store is used. Overhead of versioning is not too high. */
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" { target { vect_no_align || {! vector_alignment_reachable} } } } } */
===================================================================
@@ -67,5 +67,5 @@ int main (void)
return 0;
}
-/* { dg-final { scan-tree-dump-times "OUTER LOOP VECTORIZED" 2 "vect" { xfail vect_no_align } } } */
+/* { dg-final { scan-tree-dump-times "OUTER LOOP VECTORIZED" 2 "vect" { xfail { vect_no_align && { ! vect_hw_misalign } } } } } */
/* { dg-final { cleanup-tree-dump "vect" } } */
===================================================================
@@ -65,5 +65,5 @@ main (void)
return 0;
}
-/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" { xfail { vect_no_align || { ! vect_strided2 } } } } } */
+/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" { xfail { { vect_no_align && { ! vect_hw_misalign } } || { ! vect_strided2 } } } } } */
/* { dg-final { cleanup-tree-dump "vect" } } */
===================================================================
@@ -52,5 +52,5 @@ int main (void)
return 0;
}
-/* { dg-final { scan-tree-dump-times "OUTER LOOP VECTORIZED." 1 "vect" { xfail vect_no_align } } } */
+/* { dg-final { scan-tree-dump-times "OUTER LOOP VECTORIZED." 1 "vect" { xfail { vect_no_align && { ! vect_hw_misalign } } } } } */
/* { dg-final { cleanup-tree-dump "vect" } } */
===================================================================
@@ -51,6 +51,6 @@ int main (void)
return 0;
}
-/* { dg-final { scan-tree-dump-times "OUTER LOOP VECTORIZED." 1 "vect" { xfail { unaligned_stack || vect_no_align } } } } */
+/* { dg-final { scan-tree-dump-times "OUTER LOOP VECTORIZED." 1 "vect" { xfail { unaligned_stack || { vect_no_align && { ! vect_hw_misalign } } } } } } */
/* { dg-final { scan-tree-dump-times "vect_recog_widen_mult_pattern: detected" 1 "vect" { xfail *-*-* } } } */
/* { dg-final { cleanup-tree-dump "vect" } } */
===================================================================
@@ -90,5 +90,5 @@ int main (void)
}
/* { dg-final { scan-tree-dump-times "vectorized 2 loops" 2 "vect" } } */
-/* { dg-final { scan-tree-dump-times "Alignment of access forced using versioning" 6 "vect" { target vect_no_align } } } */
+/* { dg-final { scan-tree-dump-times "Alignment of access forced using versioning" 6 "vect" { target { vect_no_align && { ! vect_hw_misalign } } } } } */
/* { dg-final { cleanup-tree-dump "vect" } } */
===================================================================
@@ -71,5 +71,5 @@ int main (void)
return 0;
}
-/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" { xfail vect_no_align } } } */
+/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" { xfail { vect_no_align && { ! vect_hw_misalign } } } } } */
/* { dg-final { cleanup-tree-dump "vect" } } */
===================================================================
@@ -73,5 +73,5 @@ int main (void)
return 0;
}
-/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" { xfail vect_no_align } } } */
+/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" { xfail { vect_no_align && { ! vect_hw_misalign } } } } } */
/* { dg-final { cleanup-tree-dump "vect" } } */
===================================================================
@@ -50,7 +50,7 @@ int main (void)
return main1 ();
}
-/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" {xfail vect_no_align } } } */
+/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" {xfail { vect_no_align && { ! vect_hw_misalign } } } } } */
/* { dg-final { scan-tree-dump-times "dependence distance negative" 1 "vect" } } */
/* { dg-final { cleanup-tree-dump "vect" } } */
===================================================================
@@ -50,6 +50,6 @@ int main (void)
return main1 ();
}
-/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" {xfail vect_no_align } } } */
+/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" {xfail { vect_no_align && { ! vect_hw_misalign } } } } } */
/* { dg-final { scan-tree-dump-times "dependence distance negative" 1 "vect" } } */
/* { dg-final { cleanup-tree-dump "vect" } } */
===================================================================
@@ -182,6 +182,6 @@ int main ()
return main1 ();
}
-/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 4 "vect" {xfail vect_no_align } } } */
+/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 4 "vect" {xfail { vect_no_align && { ! vect_hw_misalign } } } } } */
/* { dg-final { scan-tree-dump-times "dependence distance negative" 4 "vect" } } */
/* { dg-final { cleanup-tree-dump "vect" } } */
===================================================================
@@ -18,5 +18,5 @@ void square(const float * __restrict__ a,
}
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" } } */
-/* { dg-final { scan-tree-dump-times "Alignment of access forced using versioning" 2 "vect" { target vect_no_align } } } */
+/* { dg-final { scan-tree-dump-times "Alignment of access forced using versioning" 2 "vect" { target { vect_no_align && { ! vect_hw_misalign } } } } } */
/* { dg-final { cleanup-tree-dump "vect" } } */
===================================================================
@@ -52,5 +52,5 @@ int main (int argc, char **argv)
/* The loops in VecBug and VecBug2 require versioning for alignment.
The loop in main is aligned. */
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 3 "vect" } } */
-/* { dg-final { scan-tree-dump-times "Alignment of access forced using versioning" 2 "vect" { target vect_no_align } } } */
+/* { dg-final { scan-tree-dump-times "Alignment of access forced using versioning" 2 "vect" { target { vect_no_align && { ! vect_hw_misalign } } } } } */
/* { dg-final { cleanup-tree-dump "vect" } } */
===================================================================
@@ -11,6 +11,6 @@ void f(unsigned char *s, unsigned char *d, int n)
}
}
-/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" { xfail vect_no_align } } } */
-/* { dg-final { scan-tree-dump-times "vectorizing stmts using SLP" 1 "vect" { xfail vect_no_align } } } */
+/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" { xfail { vect_no_align && { ! vect_hw_misalign } } } } } */
+/* { dg-final { scan-tree-dump-times "vectorizing stmts using SLP" 1 "vect" { xfail { vect_no_align && { ! vect_hw_misalign } } } } } */
/* { dg-final { cleanup-tree-dump "vect" } } */
===================================================================
@@ -28,8 +28,8 @@ void blockmove_NtoN_blend_noremap32 (const UINT32
}
}
-/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" {xfail vect_no_align } } } */
-/* { dg-final { scan-tree-dump-times "vectorizing stmts using SLP" 1 "vect" {xfail vect_no_align } } } */
+/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" { xfail { vect_no_align && { ! vect_hw_misalign } } } } } */
+/* { dg-final { scan-tree-dump-times "vectorizing stmts using SLP" 1 "vect" { xfail { vect_no_align && { ! vect_hw_misalign } } } } } */
/* { dg-final { cleanup-tree-dump "vect" } } */
===================================================================
@@ -31,5 +31,5 @@ foo (unsigned long n, const float *__restrict u0,
}
}
-/* { dg-final { scan-tree-dump "vectorized 1 loops" "vect" { xfail vect_no_align } } } */
+/* { dg-final { scan-tree-dump "vectorized 1 loops" "vect" { xfail { vect_no_align && { ! vect_hw_misalign } } } } } */
/* { dg-final { cleanup-tree-dump "vect" } } */
===================================================================
@@ -67,5 +67,5 @@ void test5 (int* a, int* b)
}
/* { dg-final { scan-tree-dump-times "hoist" 8 "vect" { xfail *-*-* } } } */
-/* { dg-final { scan-tree-dump-times "hoist" 3 "vect" { xfail vect_no_align } } } */
+/* { dg-final { scan-tree-dump-times "hoist" 3 "vect" { xfail { vect_no_align && { ! vect_hw_misalign } } } } } */
/* { dg-final { cleanup-tree-dump "vect" } } */
===================================================================
@@ -57,5 +57,5 @@ int main (void)
/* { dg-final { scan-tree-dump-times "vectorized 2 loops" 1 "vect" } } */
/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 0 "vect" } } */
-/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 2 "vect" { xfail { vect_no_align || { ! vect_natural_alignment } } } } } */
+/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 2 "vect" { xfail { { vect_no_align && { ! vect_hw_misalign } } || { ! vect_natural_alignment } } } } } */
/* { dg-final { cleanup-tree-dump "vect" } } */
===================================================================
@@ -100,7 +100,7 @@ int main (void)
}
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" } } */
-/* { dg-final { scan-tree-dump-times "Alignment of access forced using versioning" 2 "vect" { target vect_no_align } } } */
+/* { dg-final { scan-tree-dump-times "Alignment of access forced using versioning" 2 "vect" { target { vect_no_align && { ! vect_hw_misalign } } } } } */
/* { dg-final { scan-tree-dump-times "possible dependence between data-refs" 0 "vect" } } */
/* { dg-final { cleanup-tree-dump "vect" } } */
===================================================================
@@ -66,7 +66,7 @@ int main (void)
}
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" } } */
-/* { dg-final { scan-tree-dump-times "Alignment of access forced using versioning" 2 "vect" { target vect_no_align } } } */
+/* { dg-final { scan-tree-dump-times "Alignment of access forced using versioning" 2 "vect" { target { vect_no_align && { ! vect_hw_misalign } } } } } */
/* { dg-final { scan-tree-dump-times "possible dependence between data-refs" 0 "vect" } } */
/* { dg-final { cleanup-tree-dump "vect" } } */
===================================================================
@@ -44,8 +44,8 @@ int main (void)
}
/* The initialization induction loop (with aligned access) is also vectorized. */
-/* { dg-final { scan-tree-dump-times "vectorized 2 loops" 1 "vect" { xfail vect_no_align } } } */
-/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" { target vect_no_align } } } */
-/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 1 "vect" { xfail vect_no_align } } } */
+/* { dg-final { scan-tree-dump-times "vectorized 2 loops" 1 "vect" { xfail { vect_no_align && { ! vect_hw_misalign } } } } } */
+/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" { target { vect_no_align && { ! vect_hw_misalign } } } } } */
+/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 1 "vect" { xfail { vect_no_align && { ! vect_hw_misalign } } } } } */
/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 0 "vect" } } */
/* { dg-final { cleanup-tree-dump "vect" } } */
===================================================================
@@ -51,7 +51,7 @@ int main (void)
/* The initialization induction loop (with aligned access) is also vectorized. */
/* { dg-final { scan-tree-dump-times "vectorized 2 loops" 1 "vect" } } */
-/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 1 "vect" { xfail vect_no_align } } } */
+/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 1 "vect" { xfail { vect_no_align && { ! vect_hw_misalign } } } } } */
/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 0 "vect" } } */
-/* { dg-final { scan-tree-dump-times "Alignment of access forced using versioning." 1 "vect" {target vect_no_align } } } */
+/* { dg-final { scan-tree-dump-times "Alignment of access forced using versioning." 1 "vect" {target { vect_no_align && { ! vect_hw_misalign } } } } } */
/* { dg-final { cleanup-tree-dump "vect" } } */
===================================================================
@@ -36,9 +36,10 @@ int main (void)
return main1 ();
}
+/* vect_hw_misalign && { ! vect64 } */
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" } } */
-/* { dg-final { scan-tree-dump "Vectorizing an unaligned access" "vect" { target { vect_hw_misalign && { ! vect64 } } } } } */
+/* { dg-final { scan-tree-dump "Vectorizing an unaligned access" "vect" { target { { { ! powerpc*-*-* } && vect_hw_misalign } && { ! vect64 } } } } } */
/* { dg-final { scan-tree-dump "Alignment of access forced using peeling" "vect" { target { vector_alignment_reachable && vect64 } } } } */
/* { dg-final { scan-tree-dump-times "Alignment of access forced using versioning" 1 "vect" { target { { {! vector_alignment_reachable} || {! vect64} } && {! vect_hw_misalign} } } } } */
/* { dg-final { cleanup-tree-dump "vect" } } */
===================================================================
@@ -64,7 +64,7 @@ int main (void)
}
/* { dg-final { scan-tree-dump-times "vectorized 2 loops" 1 "vect" } } */
-/* { dg-final { scan-tree-dump-times "Alignment of access forced using versioning" 3 "vect" { target vect_no_align } } } */
+/* { dg-final { scan-tree-dump-times "Alignment of access forced using versioning" 3 "vect" { target { vect_no_align && { ! vect_hw_misalign } } } } } */
/* { dg-final { scan-tree-dump-times "Alignment of access forced using versioning" 1 "vect" { target { { ! vector_alignment_reachable } && { ! vect_element_align } } } } } */
/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 4 "vect" { xfail { vect_no_align || { { ! vector_alignment_reachable } || vect_element_align } } } } } */
/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 3 "vect" { target vect_element_align } } } */
===================================================================
@@ -65,8 +65,8 @@ int main (void)
two loads to be aligned). */
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" } } */
-/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 2 "vect" { xfail { vect_no_align } } } } */
-/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 1 "vect" { xfail { vect_no_align || {! vector_alignment_reachable} } } } } */
-/* { dg-final { scan-tree-dump-times "Alignment of access forced using versioning." 3 "vect" { target vect_no_align } } } */
+/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 2 "vect" { xfail { vect_no_align && { ! vect_hw_misalign } } } } } */
+/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 1 "vect" { xfail { { vect_no_align && { ! vect_hw_misalign } } || {! vector_alignment_reachable} } } } } */
+/* { dg-final { scan-tree-dump-times "Alignment of access forced using versioning." 3 "vect" { target { vect_no_align && { ! vect_hw_misalign } } } } } */
/* { dg-final { scan-tree-dump-times "Alignment of access forced using versioning." 1 "vect" { target { {! vector_alignment_reachable} && {{! vect_no_align} && {! vect_hw_misalign} } } } } } */
/* { dg-final { cleanup-tree-dump "vect" } } */
===================================================================
@@ -55,7 +55,7 @@ int main (void)
(The store is aligned). */
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" } } */
-/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 2 "vect" { xfail vect_no_align } } } */
+/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 2 "vect" { xfail { vect_no_align && { ! vect_hw_misalign } } } } } */
/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 0 "vect" } } */
-/* { dg-final { scan-tree-dump-times "Alignment of access forced using versioning." 2 "vect" { target vect_no_align } } } */
+/* { dg-final { scan-tree-dump-times "Alignment of access forced using versioning." 2 "vect" { target { vect_no_align && { ! vect_hw_misalign } } } } } */
/* { dg-final { cleanup-tree-dump "vect" } } */
===================================================================
@@ -61,9 +61,9 @@ int main (void)
align the store will not force the two loads to be aligned). */
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" } } */
-/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 2 "vect" { xfail { vect_no_align } } } } */
+/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 2 "vect" { xfail { vect_no_align && { ! vect_hw_misalign } } } } } */
/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 2 "vect" { target vect_hw_misalign } } } */
-/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 1 "vect" { xfail { vect_no_align || {! vector_alignment_reachable} } } } } */
-/* { dg-final { scan-tree-dump-times "Alignment of access forced using versioning." 3 "vect" { target vect_no_align } } } */
+/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 1 "vect" { xfail { { vect_no_align && { ! vect_hw_misalign } } || {! vector_alignment_reachable} } } } } */
+/* { dg-final { scan-tree-dump-times "Alignment of access forced using versioning." 3 "vect" { target { vect_no_align && { ! vect_hw_misalign } } } } } */
/* { dg-final { scan-tree-dump-times "Alignment of access forced using versioning." 1 "vect" { target { {! vector_alignment_reachable} && { {! vect_no_align } && {! vect_hw_misalign } } } } } } */
/* { dg-final { cleanup-tree-dump "vect" } } */
===================================================================
@@ -56,7 +56,7 @@ int main (void)
(The store is aligned). */
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" } } */
-/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 2 "vect" { xfail vect_no_align } } } */
+/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 2 "vect" { xfail { vect_no_align && { ! vect_hw_misalign } } } } } */
/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 0 "vect" } } */
-/* { dg-final { scan-tree-dump-times "Alignment of access forced using versioning." 2 "vect" { target vect_no_align } } } */
+/* { dg-final { scan-tree-dump-times "Alignment of access forced using versioning." 2 "vect" { target { vect_no_align && { ! vect_hw_misalign } } } } } */
/* { dg-final { cleanup-tree-dump "vect" } } */
===================================================================
@@ -67,7 +67,7 @@ int main (void)
return 0;
}
-/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" { xfail vect_no_align } } } */
+/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" { xfail { vect_no_align && { ! vect_hw_misalign } } } } } */
/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 2 "vect" { xfail { vect_no_align || vect_element_align } } } } */
/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 1 "vect" { target { vect_element_align } } } } */
/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 0 "vect" { xfail { vect_element_align } } } } */
===================================================================
@@ -68,7 +68,7 @@ int main (void)
return 0;
}
-/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" { xfail vect_no_align } } } */
+/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" { xfail { vect_no_align && { ! vect_hw_misalign } } } } } */
/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 2 "vect" { xfail { vect_no_align || vect_element_align } } } } */
/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 1 "vect" { target { vect_element_align } } } } */
/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 0 "vect" { xfail { vect_element_align } } } } */
===================================================================
@@ -46,7 +46,7 @@ int main (void)
return main1 ();
}
-/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" { xfail vect_no_align } } } */
-/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 1 "vect" { xfail vect_no_align } } } */
+/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" { xfail { vect_no_align && { ! vect_hw_misalign } } } } } */
+/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 1 "vect" { xfail { vect_no_align && { ! vect_hw_misalign } } } } } */
/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 0 "vect" } } */
/* { dg-final { cleanup-tree-dump "vect" } } */
===================================================================
@@ -52,6 +52,6 @@ int main (void)
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" } } */
-/* { dg-final { scan-tree-dump-times "Alignment of access forced using versioning" 1 "vect" { target vect_no_align } } } */
-/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 1 "vect" { xfail vect_no_align } } } */
+/* { dg-final { scan-tree-dump-times "Alignment of access forced using versioning" 1 "vect" { target { vect_no_align && { ! vect_hw_misalign } } } } } */
+/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 1 "vect" { xfail { vect_no_align && { ! vect_hw_misalign } } } } } */
/* { dg-final { cleanup-tree-dump "vect" } } */
===================================================================
@@ -44,6 +44,6 @@ int main (void)
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" } } */
-/* { dg-final { scan-tree-dump-times "Alignment of access forced using versioning" 1 "vect" { target vect_no_align } } } */
-/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 1 "vect" { xfail vect_no_align } } } */
+/* { dg-final { scan-tree-dump-times "Alignment of access forced using versioning" 1 "vect" { target { vect_no_align && { ! vect_hw_misalign } } } } } */
+/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 1 "vect" { xfail { vect_no_align && { ! vect_hw_misalign } } } } } */
/* { dg-final { cleanup-tree-dump "vect" } } */
===================================================================
@@ -49,8 +49,8 @@ int main (void)
both for the load and the store. */
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" } } */
-/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 1 "vect" { xfail { vect_no_align } } } } */
+/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 1 "vect" { xfail { vect_no_align && { ! vect_hw_misalign } } } } } */
/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 1 "vect" { target { {! vect_no_align} && { unaligned_stack && vector_alignment_reachable } } } } } */
-/* { dg-final { scan-tree-dump-times "Alignment of access forced using versioning." 1 "vect" { target { { {! unaligned_stack} && vect_no_align } || {unaligned_stack && { {! vector_alignment_reachable} && {! vect_no_align} } } } } } } */
+/* { dg-final { scan-tree-dump-times "Alignment of access forced using versioning." 1 "vect" { target { { {! unaligned_stack} && { vect_no_align && { ! vect_hw_misalign } } } || {unaligned_stack && { {! vector_alignment_reachable} && {! vect_no_align } } } } } } } */
/* { dg-final { scan-tree-dump-times "Alignment of access forced using versioning." 2 "vect" { target { { unaligned_stack && { vector_alignment_reachable && vect_no_align } } || {unaligned_stack && { {! vector_alignment_reachable} && vect_no_align } } } } } } */
/* { dg-final { cleanup-tree-dump "vect" } } */
===================================================================
@@ -48,7 +48,7 @@ int main (void)
/* Requires versioning for aliasing. */
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" } } */
-/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 1 "vect" { xfail { vect_no_align } } } } */
+/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 1 "vect" { xfail { vect_no_align && { ! vect_hw_misalign } } } } } */
/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 0 "vect" } } */
-/* { dg-final { scan-tree-dump-times "Alignment of access forced using versioning." 1 "vect" { target vect_no_align } } } */
+/* { dg-final { scan-tree-dump-times "Alignment of access forced using versioning." 1 "vect" { target { vect_no_align && { ! vect_hw_misalign } } } } } */
/* { dg-final { cleanup-tree-dump "vect" } } */
===================================================================
@@ -50,8 +50,8 @@ int main (void)
both for the load and the store. */
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" } } */
-/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 1 "vect" { xfail { vect_no_align } } } } */
+/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 1 "vect" { xfail { vect_no_align && { ! vect_hw_misalign } } } } } */
/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 1 "vect" { target { {! vect_no_align} && { unaligned_stack && vector_alignment_reachable } } } } } */
-/* { dg-final { scan-tree-dump-times "Alignment of access forced using versioning." 1 "vect" { target { { {! unaligned_stack} && vect_no_align } || {unaligned_stack && { {! vector_alignment_reachable} && {! vect_no_align} } } } } } } */
+/* { dg-final { scan-tree-dump-times "Alignment of access forced using versioning." 1 "vect" { target { { {! unaligned_stack} && { vect_no_align && { ! vect_hw_misalign } } } || {unaligned_stack && { {! vector_alignment_reachable} && { ! vect_no_align } } } } } } } */
/* { dg-final { scan-tree-dump-times "Alignment of access forced using versioning." 2 "vect" { target { { unaligned_stack && { vector_alignment_reachable && vect_no_align } } || {unaligned_stack && { {! vector_alignment_reachable} && vect_no_align } } } } } } */
/* { dg-final { cleanup-tree-dump "vect" } } */
===================================================================
@@ -48,7 +48,7 @@ int main (void)
(The store is aligned). */
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" } } */
-/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 1 "vect" { xfail { vect_no_align } } } } */
+/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 1 "vect" { xfail { vect_no_align && { ! vect_hw_misalign } } } } } */
/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 0 "vect" } } */
-/* { dg-final { scan-tree-dump-times "Alignment of access forced using versioning." 1 "vect" { target vect_no_align } } } */
+/* { dg-final { scan-tree-dump-times "Alignment of access forced using versioning." 1 "vect" { target { vect_no_align && { ! vect_hw_misalign } } } } } */
/* { dg-final { cleanup-tree-dump "vect" } } */
===================================================================
@@ -76,10 +76,10 @@ int main (void)
/* in main1: */
/* { dg-final { scan-tree-dump-times "vectorized 2 loops" 1 "vect" { target !powerpc*-*-* !i?86-*-* !x86_64-*-* } } } */
-/* { dg-final { scan-tree-dump-times "vectorized 2 loops" 1 "vect" { target vect_no_align } } } */
+/* { dg-final { scan-tree-dump-times "vectorized 2 loops" 1 "vect" { target { vect_no_align && { ! vect_hw_misalign } } } } } */
/* in main: */
-/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" { target vect_no_align } } } */
-/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 1 "vect" { xfail { vect_no_align } } } } */
+/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" { target { vect_no_align && { ! vect_hw_misalign } } } } } */
+/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 1 "vect" { xfail { vect_no_align && { ! vect_hw_misalign } } } } } */
/* { dg-final { cleanup-tree-dump "vect" } } */
===================================================================
@@ -64,6 +64,6 @@ int main (void)
/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 2 "vect" { xfail { vect_no_align || vect_element_align} } } } */
/* { dg-final { scan-tree-dump-times "Alignment of access forced using versioning" 2 "vect" { xfail { vect_no_align || vect_element_align } } } } */
-/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 0 "vect" { target vect_no_align } } } */
-/* { dg-final { scan-tree-dump-times "Alignment of access forced using versioning" 4 "vect" { target vect_no_align } } } */
+/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 0 "vect" { target { vect_no_align && { ! vect_hw_misalign } } } } } */
+/* { dg-final { scan-tree-dump-times "Alignment of access forced using versioning" 4 "vect" { target { vect_no_align && { ! vect_hw_misalign } } } } } */
/* { dg-final { cleanup-tree-dump "vect" } } */
===================================================================
@@ -46,5 +46,5 @@ int main (void)
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" } } */
/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 1 "vect" { target { {! vect_no_align} && vector_alignment_reachable } } } } */
/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 1 "vect" { xfail { { vect_no_align } || { { ! vector_alignment_reachable} || vect_element_align } } } } } */
-/* { dg-final { scan-tree-dump-times "Alignment of access forced using versioning." 1 "vect" { target { vect_no_align || { {! vector_alignment_reachable} && {! vect_element_align} } } } } } */
+/* { dg-final { scan-tree-dump-times "Alignment of access forced using versioning." 1 "vect" { target { { vect_no_align && { ! vect_hw_misalign } } || { {! vector_alignment_reachable} && {! vect_element_align} } } } } } */
/* { dg-final { cleanup-tree-dump "vect" } } */
===================================================================
@@ -51,7 +51,7 @@ int main (void)
return 0;
}
-/* { dg-final { scan-tree-dump-times "OUTER LOOP VECTORIZED" 1 "vect" { xfail vect_no_align } } } */
+/* { dg-final { scan-tree-dump-times "OUTER LOOP VECTORIZED" 1 "vect" { xfail { vect_no_align && { ! vect_hw_misalign } } } } } */
/* { dg-final { cleanup-tree-dump "vect" } } */
===================================================================
@@ -59,7 +59,7 @@ int main (void)
return 0;
}
-/* { dg-final { scan-tree-dump-times "OUTER LOOP VECTORIZED" 1 "vect" { xfail vect_no_align } } } */
+/* { dg-final { scan-tree-dump-times "OUTER LOOP VECTORIZED" 1 "vect" { xfail { vect_no_align && { ! vect_hw_misalign } } } } } */
/* { dg-final { cleanup-tree-dump "vect" } } */
===================================================================
@@ -56,7 +56,7 @@ int main (void)
return 0;
}
-/* { dg-final { scan-tree-dump-times "OUTER LOOP VECTORIZED" 1 "vect" { xfail vect_no_align } } } */
+/* { dg-final { scan-tree-dump-times "OUTER LOOP VECTORIZED" 1 "vect" { xfail { vect_no_align && { ! vect_hw_misalign } } } } } */
/* { dg-final { cleanup-tree-dump "vect" } } */
===================================================================
@@ -82,5 +82,5 @@ main (void)
return 0;
}
-/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" { xfail { vect_no_align || { ! vect_strided2 } } } } } */
+/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" { xfail { { vect_no_align && { ! vect_hw_misalign } } || { ! vect_strided2 } } } } } */
/* { dg-final { cleanup-tree-dump "vect" } } */
===================================================================
@@ -81,8 +81,8 @@ int main (void)
return 0;
}
-/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 2 "vect" { xfail { vect_no_align } } } } */
-/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 2 "vect" { xfail {{ vect_no_align } || {vect_sizes_32B_16B }}} } } */
-/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 4 "vect" { xfail {{ vect_no_align } || {vect_sizes_32B_16B }}} } } */
+/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 2 "vect" { xfail { vect_no_align && { ! vect_hw_misalign } } } } } */
+/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 2 "vect" { xfail {{ vect_no_align && { ! vect_hw_misalign } } || {vect_sizes_32B_16B }}} } } */
+/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 4 "vect" { xfail {{ vect_no_align && { ! vect_hw_misalign } } || {vect_sizes_32B_16B }}} } } */
/* { dg-final { cleanup-tree-dump "vect" } } */
===================================================================
@@ -54,7 +54,7 @@ int main (void)
}
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" } } */
-/* { dg-final { scan-tree-dump-times "Alignment of access forced using versioning" 3 "vect" { target vect_no_align } } } */
-/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 3 "vect" {xfail { vect_no_align } } } } */
+/* { dg-final { scan-tree-dump-times "Alignment of access forced using versioning" 3 "vect" { target { vect_no_align && { ! vect_hw_misalign } } } } } */
+/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 3 "vect" {xfail { vect_no_align && { ! vect_hw_misalign } } } } } */
/* { dg-final { cleanup-tree-dump "vect" } } */
===================================================================
@@ -92,7 +92,7 @@ int main (void)
return 0;
}
-/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 2 "vect" { xfail { vect_no_align } } } } */
+/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 2 "vect" { xfail { vect_no_align && { ! vect_hw_misalign } } } } } */
/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 0 "vect" { target { vect_element_align} } } } */
/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 2 "vect" { xfail { vect_no_align || vect_element_align } } } } */
/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 8 "vect" { xfail { vect_no_align || vect_element_align } } } } */
===================================================================
@@ -61,7 +61,7 @@ int main (void)
}
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" { xfail { sparc*-*-* && ilp32 } }} } */
-/* { dg-final { scan-tree-dump-times "Alignment of access forced using versioning" 6 "vect" { target vect_no_align } } } */
-/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 6 "vect" {xfail { vect_no_align } } } } */
+/* { dg-final { scan-tree-dump-times "Alignment of access forced using versioning" 6 "vect" { target { vect_no_align && { ! vect_hw_misalign } } } } } */
+/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 6 "vect" {xfail { vect_no_align && { ! vect_hw_misalign } } } } } */
/* { dg-final { cleanup-tree-dump "vect" } } */
===================================================================
@@ -43,6 +43,6 @@ int main ()
return 0;
}
-/* { dg-final { scan-tree-dump-times "OUTER LOOP VECTORIZED" 1 "vect" { xfail vect_no_align } } } */
+/* { dg-final { scan-tree-dump-times "OUTER LOOP VECTORIZED" 1 "vect" { xfail { vect_no_align && { ! vect_hw_misalign } } } } } */
/* { dg-final { cleanup-tree-dump "vect" } } */
===================================================================
@@ -42,6 +42,6 @@ int main ()
return 0;
}
-/* { dg-final { scan-tree-dump-times "OUTER LOOP VECTORIZED" 1 "vect" { xfail vect_no_align } } } */
+/* { dg-final { scan-tree-dump-times "OUTER LOOP VECTORIZED" 1 "vect" { xfail { vect_no_align && { ! vect_hw_misalign } } } } } */
/* { dg-final { cleanup-tree-dump "vect" } } */
===================================================================
@@ -48,6 +48,6 @@ int main (void)
return 0;
}
-/* { dg-final { scan-tree-dump-times "OUTER LOOP VECTORIZED" 1 "vect" { xfail vect_no_align } } } */
+/* { dg-final { scan-tree-dump-times "OUTER LOOP VECTORIZED" 1 "vect" { xfail { vect_no_align && { ! vect_hw_misalign } } } } } */
/* { dg-final { scan-tree-dump-times "step doesn't divide the vector-size" 1 "vect" } } */
/* { dg-final { cleanup-tree-dump "vect" } } */
===================================================================
@@ -48,6 +48,6 @@ int main (void)
return 0;
}
-/* { dg-final { scan-tree-dump-times "OUTER LOOP VECTORIZED" 1 "vect" { xfail vect_no_align } } } */
+/* { dg-final { scan-tree-dump-times "OUTER LOOP VECTORIZED" 1 "vect" { xfail { vect_no_align && { ! vect_hw_misalign } } } } } */
/* { dg-final { scan-tree-dump-times "step doesn't divide the vector-size" 1 "vect" } } */
/* { dg-final { cleanup-tree-dump "vect" } } */
===================================================================
@@ -78,5 +78,5 @@ int main ()
is known. */
/* { dg-final { scan-tree-dump-times "not vectorized: possible dependence between data-refs" 1 "vect" { xfail *-*-* } } } */
/* { dg-final { scan-tree-dump-times "OUTER LOOP VECTORIZED" 1 "vect" } } */
-/* { dg-final { scan-tree-dump "zero step in outer loop." "vect" { xfail vect_no_align } } } */
+/* { dg-final { scan-tree-dump "zero step in outer loop." "vect" { xfail { vect_no_align && { ! vect_hw_misalign } } } } } */
/* { dg-final { cleanup-tree-dump "vect" } } */
===================================================================
@@ -70,5 +70,5 @@ int main (void)
return 0;
}
-/* { dg-final { scan-tree-dump-times "OUTER LOOP VECTORIZED" 2 "vect" { xfail vect_no_align } } } */
+/* { dg-final { scan-tree-dump-times "OUTER LOOP VECTORIZED" 2 "vect" { xfail { vect_no_align && { ! vect_hw_misalign } } } } } */
/* { dg-final { cleanup-tree-dump "vect" } } */
===================================================================
@@ -74,5 +74,5 @@ int main (void)
return 0;
}
-/* { dg-final { scan-tree-dump-times "OUTER LOOP VECTORIZED" 2 "vect" { xfail vect_no_align } } } */
+/* { dg-final { scan-tree-dump-times "OUTER LOOP VECTORIZED" 2 "vect" { xfail { vect_no_align && { ! vect_hw_misalign } } } } } */
/* { dg-final { cleanup-tree-dump "vect" } } */
===================================================================
@@ -74,5 +74,5 @@ int main (void)
return 0;
}
-/* { dg-final { scan-tree-dump-times "OUTER LOOP VECTORIZED" 2 "vect" { xfail vect_no_align } } } */
+/* { dg-final { scan-tree-dump-times "OUTER LOOP VECTORIZED" 2 "vect" { xfail { vect_no_align && { ! vect_hw_misalign } } } } } */
/* { dg-final { cleanup-tree-dump "vect" } } */
===================================================================
@@ -70,5 +70,5 @@ int main (void)
return 0;
}
-/* { dg-final { scan-tree-dump-times "OUTER LOOP VECTORIZED" 2 "vect" { xfail vect_no_align } } } */
+/* { dg-final { scan-tree-dump-times "OUTER LOOP VECTORIZED" 2 "vect" { xfail { vect_no_align && { ! vect_hw_misalign } } } } } */
/* { dg-final { cleanup-tree-dump "vect" } } */
===================================================================
@@ -48,7 +48,7 @@ int main (void)
return main1 ();
}
-/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" { xfail vect_no_align } } } */
-/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 1 "vect" { xfail { { vect_no_align } || {vect_sizes_32B_16B } } } } } */
-/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 1 "vect" { xfail { { vect_no_align } || {vect_sizes_32B_16B } } } } } */
+/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" { xfail { vect_no_align && { ! vect_hw_misalign } } } } } */
+/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 1 "vect" { xfail { { vect_no_align && { ! vect_hw_misalign } } || {vect_sizes_32B_16B } } } } } */
+/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 1 "vect" { xfail { { vect_no_align && { ! vect_hw_misalign } } || {vect_sizes_32B_16B } } } } } */
/* { dg-final { cleanup-tree-dump "vect" } } */
===================================================================
@@ -45,7 +45,7 @@ int main (void)
return main1 ();
}
-/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" { xfail vect_no_align } } } */
-/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 1 "vect" { xfail vect_no_align } } } */
+/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" { xfail { vect_no_align && { ! vect_hw_misalign } } } } } */
+/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 1 "vect" { xfail { vect_no_align && { ! vect_hw_misalign } } } } } */
/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 0 "vect" } } */
/* { dg-final { cleanup-tree-dump "vect" } } */
===================================================================
@@ -12,5 +12,5 @@ void foo (void)
res[i] = data[i] + data[i + 1];
}
-/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" { xfail vect_no_align } } } */
+/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" { xfail { vect_no_align && { ! vect_hw_misalign } } } } } */
/* { dg-final { cleanup-tree-dump "vect" } } */
===================================================================
@@ -59,7 +59,7 @@ int main (void)
}
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" } } */
-/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 0 "vect" {xfail {! vect_hw_misalign } } } } */
+/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 0 "vect" {xfail { {! vect_hw_misalign } || powerpc*-*-* } } } } */
/* { dg-final { scan-tree-dump-times "Alignment of access forced using versioning" 0 "vect" } } */
-/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 4 "vect" {xfail {! vect_hw_misalign } } } } */
+/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 4 "vect" {xfail { {! vect_hw_misalign } || powerpc*-*-* } } } } */
/* { dg-final { cleanup-tree-dump "vect" } } */
===================================================================
@@ -55,7 +55,7 @@ int main (void)
}
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" } } */
-/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 0 "vect" {xfail {! vect_hw_misalign } } } } */
+/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 0 "vect" {xfail { {! vect_hw_misalign } || powerpc*-*-* } } } } */
/* { dg-final { scan-tree-dump-times "Alignment of access forced using versioning" 0 "vect" } } */
-/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 3 "vect" {xfail {! vect_hw_misalign } } } } */
+/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 3 "vect" {xfail { {! vect_hw_misalign } || powerpc*-*-* } } } } */
/* { dg-final { cleanup-tree-dump "vect" } } */
===================================================================
@@ -59,7 +59,7 @@ int main (void)
}
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" } } */
-/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 0 "vect" {xfail {! vect_hw_misalign } } } } */
+/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 0 "vect" {xfail { {! vect_hw_misalign } || powerpc*-*-* } } } } */
/* { dg-final { scan-tree-dump-times "Alignment of access forced using versioning" 0 "vect" } } */
-/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 4 "vect" {xfail {! vect_hw_misalign } } } } */
+/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 4 "vect" {xfail { {! vect_hw_misalign } || powerpc*-*-* } } } } */
/* { dg-final { cleanup-tree-dump "vect" } } */
===================================================================
@@ -59,7 +59,7 @@ int main (void)
}
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" } } */
-/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 0 "vect" {xfail {! vect_hw_misalign } } } } */
+/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 0 "vect" {xfail { {! vect_hw_misalign } || powerpc*-*-* } } } } */
/* { dg-final { scan-tree-dump-times "Alignment of access forced using versioning" 0 "vect" } } */
-/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 4 "vect" {xfail {! vect_hw_misalign } } } } */
+/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 4 "vect" {xfail { {! vect_hw_misalign } || powerpc*-*-* } } } } */
/* { dg-final { cleanup-tree-dump "vect" } } */
===================================================================
@@ -15,8 +15,8 @@ END
! support unaligned loads).
! { dg-final { scan-tree-dump-times "vectorized 3 loops" 1 "vect" } }
-! { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 3 "vect" { xfail { vect_no_align || { ! vector_alignment_reachable } } } } }
-! { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 2 "vect" { target { vect_no_align && { ! vector_alignment_reachable } } } } }
-! { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 2 "vect" { xfail { vect_no_align } } } }
-! { dg-final { scan-tree-dump-times "Alignment of access forced using versioning." 3 "vect" {target { vect_no_align || { { ! vector_alignment_reachable } && { ! vect_hw_misalign } } } } } }
+! { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 3 "vect" { xfail { { vect_no_align && { ! vect_hw_misalign } } || { ! vector_alignment_reachable } } } } }
+! { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 2 "vect" { target { { vect_no_align && { ! vect_hw_misalign } } && { ! vector_alignment_reachable } } } } }
+! { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 2 "vect" { xfail { vect_no_align && { ! vect_hw_misalign } } } } }
+! { dg-final { scan-tree-dump-times "Alignment of access forced using versioning." 3 "vect" {target { { vect_no_align && { ! vect_hw_misalign } } || { { ! vector_alignment_reachable } && { ! vect_hw_misalign } } } } } }
! { dg-final { cleanup-tree-dump "vect" } }
===================================================================
@@ -6,10 +6,10 @@ DIMENSION X(N), Y(N)
Y = Y + A * X
END
-! { dg-final { scan-tree-dump-times "Alignment of access forced using versioning" 3 "vect" { target vect_no_align } } }
+! { dg-final { scan-tree-dump-times "Alignment of access forced using versioning" 3 "vect" { target { vect_no_align && { ! vect_hw_misalign } } } } }
! { dg-final { scan-tree-dump-times "Alignment of access forced using versioning" 1 "vect" { target { {! vect_no_align} && { {! vector_alignment_reachable} && {! vect_hw_misalign} } } } } }
! { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 2 "vect" { target { {! vect_no_align} && { {! vector_alignment_reachable} && {! vect_hw_misalign} } } } } }
-! { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 1 "vect" { xfail { vect_no_align || {! vector_alignment_reachable}} } } }
-! { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 1 "vect" { xfail { { vect_no_align } || { ! vector_alignment_reachable} } } } }
+! { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 1 "vect" { xfail { { vect_no_align && { ! vect_hw_misalign } } || {! vector_alignment_reachable}} } } }
+! { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 1 "vect" { xfail { { vect_no_align && { ! vect_hw_misalign } } || { ! vector_alignment_reachable} } } } }
! { dg-final { cleanup-tree-dump "vect" } }
===================================================================
@@ -10,8 +10,8 @@ Y = Y + A * X
END
! { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" } }
-! { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 1 "vect" { xfail { { vect_no_align } || {! vector_alignment_reachable} } } } }
-! { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 1 "vect" { xfail { { vect_no_align } || {! vector_alignment_reachable} } } } }
+! { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 1 "vect" { xfail { { vect_no_align && { ! vect_hw_misalign } } || {! vector_alignment_reachable} } } } }
+! { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 1 "vect" { xfail { { vect_no_align && { ! vect_hw_misalign } } || {! vector_alignment_reachable} } } } }
! { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 2 "vect" { target { {! vector_alignment_reachable} && {! vect_hw_misalign} } } } }
! { dg-final { scan-tree-dump-times "accesses have the same alignment." 1 "vect" } }
! { dg-final { cleanup-tree-dump "vect" } }
===================================================================
@@ -36,8 +36,8 @@
end
! { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" } }
-! { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 1 "vect" { xfail { vect_no_align || {! vector_alignment_reachable} } } } }
-! { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 1 "vect" { xfail { vect_no_align } } } }
-! { dg-final { scan-tree-dump-times "Alignment of access forced using versioning." 2 "vect" { target { vect_no_align } } } }
+! { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 1 "vect" { xfail { { vect_no_align && { ! vect_hw_misalign } } || {! vector_alignment_reachable} } } } }
+! { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 1 "vect" { xfail { vect_no_align && { ! vect_hw_misalign } } } } }
+! { dg-final { scan-tree-dump-times "Alignment of access forced using versioning." 2 "vect" { target { vect_no_align && { ! vect_hw_misalign } } } } }
! { dg-final { scan-tree-dump-times "Alignment of access forced using versioning." 1 "vect" { target { {! vector_alignment_reachable} && {! vect_hw_misalign} } } } }
! { dg-final { cleanup-tree-dump "vect" } }
===================================================================
@@ -4164,6 +4164,7 @@ proc check_effective_target_vect_no_align { } {
|| [istarget sparc*-*-*]
|| [istarget ia64-*-*]
|| [check_effective_target_arm_vect_no_misalign]
+ || ([istarget powerpc*-*-*] && [check_p8vector_hw_available])
|| ([istarget mips*-*-*]
&& [check_effective_target_mips_loongson]) } {
set et_vect_no_align_saved 1
@@ -4185,6 +4186,7 @@ proc check_effective_target_vect_hw_misalign { } {
} else {
set et_vect_hw_misalign_saved 0
if { [istarget i?86-*-*] || [istarget x86_64-*-*]
+ || ([istarget powerpc*-*-*] && [check_p8vector_hw_available])
|| [istarget aarch64*-*-*] } {
set et_vect_hw_misalign_saved 1
}
Hi, The POWER8 processor greatly improves performance of unaligned vector loads and stores. Except for certain corner cases the compiler can't readily track, an unaligned vector load or store performs equivalently to an aligned one. To exploit this in the auto-vectorizer requires two changes. The simple one is to change the cost model to reflect the cheaper cost for POWER8 versus previous processors. Additionally, we want to avoid generating the masked-load sequence (load/load/lvsl/vperm) used to force alignment of unaligned loads. Of course we must be careful to still use this sequence if -mno-vsx is selected for POWER8 for some reason. (Note that POWER7 supported unaligned vector memory references, but for best performance we have chosen to use the masked-load sequence for that processor. This is no longer optimal for POWER8.) The code changes in the rs6000 back end are simple enough, but unfortunately there is quite a bit of test case fallout. There are two predicates in target-supports.exp that need adjustment: * vect_no_align, which returns 1 iff the target plus current options does not support a vector alignment mechanism; and * vect_hw_misalign, which returns 1 iff the target supports a misaligned vector access. Unlike previous processors, for POWER8+VSX we want both of these predicates to return 1. In the former case, it isn't that we don't support a vector alignment mechanism, but under no circumstances do we want to use it when we have a misaligned vector access instruction that performs well. As a result of these changes, many loops will now auto-vectorize on P8 that would not on P7. Unfortunately, this causes many tests to fail, even with the changes to target-supports.exp. The primary reason is that the tests are testing vect_no_align in many places, where the correct thing to test is vect_no_align && !vect_hw_misalign. That is, the test condition should fire not just when there isn't a vector alignment mechanism, but only when the target also doesn't support a direct misaligned vector memory access. The reason this "shortcut" has worked up till now is that the set of targets for which vect_no_align and vect_hw_misalign both return 1 has been empty. Thus vect_no_align has been functionally equivalent to vect_no-align && !vect_hw_misalign. Happily, this means it is also safe to make that substitution in the failing tests without affecting other targets. So, this patch contains three parts: * Changes to rs6000.c and vector.md for the vectorization support; * Changes to target-supports.exp to reflect POWER8's characteristics; and * Numerous changes to fix test cases to make them pass/fail correctly for POWER8. I've tested this on POWER8 BE, POWER8 LE, and POWER7 BE, with no regressions. A handful of existing POWER8 failures are also corrected as a happy side effect. Since we're in stage 4, I obviously need to hold off till the next release, but pending that, will this be ok for trunk? After it burns in I would like to backport it to 4.8, 4.9, and 5. Thanks! Bill [gcc] 2015-01-23 Bill Schmidt <wschmidt@linux.vnet.ibm.com> * config/rs6000/rs6000.c (rs6000_builtin_mask_for_load): Return 0 for POWER8 so that the vectorizer will use direct unaligned loads. (rs6000_builtin_support_vector_misalignment): Always return true for VSX + POWER8. (rs6000_builtin_vectorization_cost): Cost of unaligned loads and stores on VSX + POWER8 is almost always the same as the cost of an aligned load or store, so model it that way. * config/rs6000/vector.md (movmisalign<mode>): Misaligned loads and stores are always permissible for VSX + POWER8. [gcc/testsuite] 2015-01-23 Bill Schmidt <wschmidt@linux.vnet.ibm.com> * gcc.dg/vect/bb-slp-24.c: Exclude test for POWER8. * gcc.dg/vect/bb-slp-25.c: Likewise. * gcc.dg/vect/bb-slp-29.c: Likewise. * gcc.dg/vect/bb-slp-32.c: Replace vect_no_align with vect_no_align && { ! vect_hw_misalign }. * gcc.dg/vect/bb-slp-9.c: Likewise. * gcc.dg/vect/costmodel/ppc/costmodel-slp-33.c: Exclude test for vect_hw_misalign. * gcc.dg/vect/costmodel/ppc/costmodel-vect-31a.c: Likewise. * gcc.dg/vect/costmodel/ppc/costmodel-vect-76b.c: Adjust tests to account for POWER8, where peeling for alignment is not needed. * gcc.dg/vect/costmodel/ppc/costmodel-vect-outer-fir.c: Replace vect_no_align with vect_no_align && { ! vect_hw_misalign }. * gcc.dg.vect.if-cvt-stores-vect-ifcvt-18.c: Likewise. * gcc.dg/vect/no-scevccp-outer-6-global.c: Likewise. * gcc.dg/vect/no-scevccp-outer-6.c: Likewise. * gcc.dg/vect/no-vfa-vect-43.c: Likewise. * gcc.dg/vect/no-vfa-vect-57.c: Likewise. * gcc.dg/vect/no-vfa-vect-61.c: Likewise. * gcc.dg/vect/no-vfa-vect-depend-1.c: Likewise. * gcc.dg/vect/no-vfa-vect-depend-2.c: Likewise. * gcc.dg/vect/no-vfa-vect-depend-3.c: Likewise. * gcc.dg/vect/pr16105.c: Likewise. * gcc.dg/vect/pr20122.c: Likewise. * gcc.dg/vect/pr33804.c: Likewise. * gcc.dg/vect/pr33953.c: Likewise. * gcc.dg/vect/pr56787.c: Likewise. * gcc.dg/vect/pr58508.c: Likewise. * gcc.dg/vect/slp-25.c: Likewise. * gcc.dg/vect/vect-105-bit-array.c: Likewise. * gcc.dg/vect/vect-105.c: Likewise. * gcc.dg/vect/vect-27.c: Likewise. * gcc.dg/vect/vect-29.c: Likewise. * gcc.dg/vect/vect-33.c: Exclude unaligned access test for POWER8. * gcc.dg/vect/vect-42.c: Replace vect_no_align with vect_no_align && { ! vect_hw_misalign }. * gcc.dg/vect/vect-44.c: Likewise. * gcc.dg/vect/vect-48.c: Likewise. * gcc.dg/vect/vect-50.c: Likewise. * gcc.dg/vect/vect-52.c: Likewise. * gcc.dg/vect/vect-56.c: Likewise. * gcc.dg/vect/vect-60.c: Likewise. * gcc.dg/vect/vect-72.c: Likewise. * gcc.dg/vect/vect-75-big-array.c: Likewise. * gcc.dg/vect/vect-75.c: Likewise. * gcc.dg/vect/vect-77-alignchecks.c: Likewise. * gcc.dg/vect/vect-77-global.c: Likewise. * gcc.dg/vect/vect-78-alignchecks.c: Likewise. * gcc.dg/vect/vect-78-global.c: Likewise. * gcc.dg/vect/vect-93.c: Likewise. * gcc.dg/vect/vect-95.c: Likewise. * gcc.dg/vect/vect-96.c: Likewise. * gcc.dg/vect/vect-cond-1.c: Likewise. * gcc.dg/vect/vect-cond-3.c: Likewise. * gcc.dg/vect/vect-cond-4.c: Likewise. * gcc.dg/vect/vect-cselim-1.c: Likewise. * gcc.dg/vect/vect-multitypes-1.c: Likewise. * gcc.dg/vect/vect-multitypes-3.c: Likewise. * gcc.dg/vect/vect-multitypes-4.c: Likewise. * gcc.dg/vect/vect-multitypes-6.c: Likewise. * gcc.dg/vect/vect-nest-cycle-1.c: Likewise. * gcc.dg/vect/vect-nest-cycle-2.c: Likewise. * gcc.dg/vect/vect-outer-3a-big-array.c: Likewise. * gcc.dg/vect/vect-outer-3a.c: Likewise. * gcc.dg/vect/vect-outer-5.c: Likewise. * gcc.dg/vect/vect-outer-fir-big-array.c: Likewise. * gcc.dg/vect/vect-outer-fir-lb-big-array.c: Likewise. * gcc.dg/vect/vect-outer-fir-lb.c: Likewise. * gcc.dg/vect/vect-outer-fir.c: Likewise. * gcc.dg/vect/vect-peel-3.c: Likewise. * gcc.dg/vect/vect-peel-4.c: Likewise. * gcc.dg/vect/vect-pre-interact.c: Likewise. * gcc.target/powerpc/vsx-vectorize-2.c: Exclude test for POWER8. * gcc.target/powerpc/vsx-vectorize-4.c: Likewise. * gcc.target/powerpc/vsx-vectorize-6.c: Likewise. * gcc.target/powerpc/vsx-vectorize-7.c: Likewise. * gfortran.dg/vect/vect-2.f90: Replace vect_no_align with vect_no_align && { ! vect_hw_misalign }. * gfortran.dg/vect/vect-3.f90: Likewise. * gfortran.dg/vect/vect-4.f90: Likewise. * gfortran.dg/vect/vect-5.f90: Likewise. * lib/target-supports.exp (check_effective_target_vect_no_align): Return 1 for POWER8. (check_effective_target_vect_hw_misalign): Return 1 for POWER8.